1,963 Hits in 3.4 sec

Secure and Energy-Efficient Computational Offloading Using LSTM in Mobile Edge Computing

Muhammad Arif, F. Ajesh, Shermin Shamsudheen, Muhammad Shahzad, Mamoun Alazab
2022 Security and Communication Networks  
, reduce energy consumption, and bring much security to the devices due to the firewall nature of LSTM.  ...  The prediction of the computational tasks is done using the LSTM algorithm, the strategy for computation offloading of mobile devices is based on the prediction of tasks, and the migration of tasks for  ...  [23] proposed a deep reinforcement learning strategy to strengthen the entire offloading system.  ... 
doi:10.1155/2022/4937588 fatcat:cm54h5tfcze43btke5hdxctbqi

Spectrum Efficiency and Energy Efficiency in Wireless Communication Networks

Yi Qian
2020 IEEE wireless communications  
The second article, "Overcoming the Channel Estimation Barrier in Massive MIMO Communication via Deep Learning" by Z.  ...  Using high performance and very low latency communication links to offload mobile device computing load into nearby powerful computing clouds becomes an essential direction to pursue.  ...  Prior to joining UNL, he worked in the telecommunications industry, academia, and government.  ... 
doi:10.1109/mwc.2020.9241874 fatcat:durjgqmw5zclnm2trbqp3hgt6u

DRL-Based Edge Computing Model to Offload the FIFA World Cup Traffic

Hongyi Li, Xinrui Che, Jianhui Lv
2020 Mobile Information Systems  
Then, the Deep Reinforcement Learning (DRL) is used to provide the traffic scheduling method and minimize the scheduling time of application programs.  ...  At first, we present the system framework based on the Mobile Edge Computing (MEC) paradigm, which supports transferring the FIFA World Cup traffic to the mobile edge servers.  ...  In [34] , a deep-Q network based task offloading and resource allocation algorithm for the MEC was proposed, where each mobile terminal had the multiple tasks offloaded to the edge server.  ... 
doi:10.1155/2020/8825643 fatcat:qt5eeg6anfgudp4gr66gxlwoju

Implementing Practical DNN-based Object Detection Offloading Decision for Maximizing Detection Performance of Mobile Edge Devices

Giha Yoon, Geun-Yong Kim, Hark Yoo, Sung Chang Kim, Ryangsoo Kim
2021 IEEE Access  
Recently, various efforts to design deep learning offloading frameworks have been made to support multiple mobile edge devices. Zhou et al.  ...  In [21] - [24] , the authors applied deep learning approaches, supervised learning and reinforcement learning to find the optimal offloading decision policy.  ... 
doi:10.1109/access.2021.3118731 fatcat:6sesuixmx5gttoelrr7bgphdhy

Dynamic Offloading for Energy Harvesting Mobile Edge Computing: Architecture, Case Studies, and Future Directions

Bin Li, Zesong Fei, Jian Shen, Xiao Jiang, Xiaoxiong Zhong
2019 IEEE Access  
INDEX TERMS Mobile edge computing, energy harvesting, device-to-device (D2D) communication, computation offloading.  ...  In this paper, we propose a wireless powered MEC network architecture that employs device-to-device (D2D) communications underlaying heterogeneous networks (HetNets) to enable the computational tasks offloading  ...  If mobile device has good VOLUME 7, 2019 cellular connection, the computation task can be delivered to the associated SBS via wireless local network.  ... 
doi:10.1109/access.2019.2922362 fatcat:pqnjxyehvzat5jey4fq3dzcdsy

Towards Mobile Edge Computing: Taxonomy, Challenges, Applications and Future Realms

Junaid Qadir
The Mobile Edge Computing (MEC) paradigm is one of the effective solutions, which brings the cloud computing services to the proximityof the edge network and leverages the available resources.  ...  In addition, applications related to the MEC platform are presented. Openresearch challenges, future directions, and lessons learned in area of the MEC are provided for further futureinvestigation.  ...  AI is a pioneering solution for various key parameters such as service migration, edge server selection, user mobility, and cloudlet likelihood connection. 2) DEEP LEARNING-BASED MEC SYSTEMS Deep learning  ... 
doi:10.6084/m9.figshare.13147607.v1 fatcat:ni77edahzfhifgqtl22o565ygi

AVEC: Accelerator Virtualization in Cloud-Edge Computing for Deep Learning Libraries [article]

Jason Kennedy, Blesson Varghese, Carlos Reaño
2021 arXiv   pre-print
This is achieved by offloading computationally intensive workloads, such as deep learning from user devices to the edge.  ...  This paper therefore sets out to investigate the potential of GPU accelerator virtualization to improve the performance of deep learning workloads in a cloud-edge environment.  ...  For example, deep learning is an important class of workloads that has found multiple applications in modern mobile apps [3] , [4] and smart cities [27] .  ... 
arXiv:2103.04930v1 fatcat:6bsp4x3ixrfglnvtpmxk77i2fq

Security and Cost-Aware Computation Offloading via Deep Reinforcement Learning in Mobile Edge Computing

Binbin Huang, Yangyang Li, Zhongjin Li, Linxuan Pan, Shangguang Wang, Yunqiu Xu, Haiyang Hu
2019 Wireless Communications and Mobile Computing  
Then, based on the popular deep reinforcement learning approach, deep Q-network (DQN), the optimal offloading policy for the proposed problem is derived.  ...  Fortunately, mobile edge computing, which enables mobile devices to offload computation tasks to edge servers with abundant computing resources, can significantly meet the ever-increasing computation demands  ...  result is sent to the mobile device.  ... 
doi:10.1155/2019/3816237 fatcat:to6jujhcxrf5lieqos3efwctue

Vehicular Edge Computing via Deep Reinforcement Learning [article]

Qi Qi, Zhanyu Ma
2020 arXiv   pre-print
We formulate the offloading decision of multi-task in a service as a long-term planning problem, and explores the recent deep reinforcement learning to obtain the optimal solution.  ...  The simulation results show that KD service offloading decision converges quickly, adapts to different conditions, and outperforms the greedy offloading decision algorithm.  ...  Combinatorial Optimization based on Deep Reinforcement Learning Deep learning method has better generalization ability, without the need to formulate the environment.  ... 
arXiv:1901.04290v3 fatcat:2ubcmtfm7ne3djdoj6pwxm6aie

Deep Learning at the Mobile Edge: Opportunities for 5G Networks

Miranda McClellan, Cristina Cervelló-Pastor, Sebastià Sallent
2020 Applied Sciences  
Machine Learning (ML) is leveraged within mobile edge computing to predict changes in demand based on cultural events, natural disasters, or daily commute patterns, and it prepares the network by automatically  ...  Mobile edge computing (MEC) within 5G networks brings the power of cloud computing, storage, and analysis closer to the end user.  ...  Identifies communities of mobile users and predictive device-to-device caching [70] RL Optimizes scheduling of offloaded tasks for vehicular networks Offloading [71] RL Minimizes energy, computation  ... 
doi:10.3390/app10144735 fatcat:ytrnh35x6zbxbki3zg435xqacu

Edge computational task offloading scheme using reinforcement learning for IIoT scenario

Md. Sajjad Hossain, Cosmas Ifeanyi Nwakanma, Jae Min Lee, Dong-Seong Kim
2020 ICT Express  
Abstract In this paper, end devices are considered here as agent, which makes its decisions on whether the network will offload the computation tasks to the edge devices or not.  ...  An optimal binary computational offloading decision is proposed and then reinforcement learning is introduced to solve the problem.  ...  Where as in [10] the authors proposed an online based model free deep reinforcement learning based computation offloading to facilitate the mobile edge computing paradigm.  ... 
doi:10.1016/j.icte.2020.06.002 fatcat:57e2giprxrfptc56dp7w7puyqu

Towards Mobile Edge Computing: Taxonomy, Challenges, Applications and Future Realms

Junaid Qadir, Beatriz Sainz-De-Abajo, Anwar Khan, Begona Garcia-Zapirain, Isabel De La Torre-Diez, Hasan Mahmood
2020 IEEE Access  
AI is a pioneering solution for various key parameters such as service migration, edge server selection, user mobility, and cloudlet likelihood connection. 2) Deep learning-based MEC systems Deep learning  ...  In addition, mobile devices can offload and access services via radio access such as Wi-Fi, 3G, LTE, Wi-MAX, and 5G.  ... 
doi:10.1109/access.2020.3026938 fatcat:rfboh327g5flnn3a6ueq5tv44q

UbiPriSEQ—Deep Reinforcement Learning to Manage Privacy, Security, Energy, and QoS in 5G IoT HetNets

Thaha Mohammed, Aiiad Albeshri, Iyad Katib, Rashid Mehmood
2020 Applied Sciences  
This paper proposes the UbiPriSEQ framework that uses Deep Reinforcement Learning (DRL) to adaptively, dynamically, and holistically optimize QoS, energy-efficiency, security, and privacy.  ...  A particular challenge in this context is to preserve privacy and security while delivering quality of service (QoS) and energy-efficiency.  ...  This multi-agent learning enables the devices to learn and decide the offloading decisions based on the strategies taken by the network module to provide security.  ... 
doi:10.3390/app10207120 fatcat:pnlew4tabjeejn7r6awih6ov7e

Computation offloading technique for energy efficiency of smart devices

Jaejun Ko, Young-June Choi, Rajib Paul
2021 Journal of Cloud Computing: Advances, Systems and Applications  
According to the performance evaluation, offloading from wearable devices to smartphones and offloading once to cloud server can reduce energy consumption significantly.  ...  We propose a computation offloading technique that offloads from the smartphone to the cloud server considering the decision model of both wearable devices and smartphones.  ...  to offload the mobile device once to the cloud server.  ... 
doi:10.1186/s13677-021-00260-8 fatcat:pzd5e6bw5vci5atseot4b6hxmy

Federated Learning for Internet of Things: A Comprehensive Survey [article]

Dinh C. Nguyen, Ming Ding, Pubudu N. Pathirana, Aruna Seneviratne, Jun Li, H. Vincent Poor
2021 arXiv   pre-print
Particularly, we explore and analyze the potential of FL for enabling a wide range of IoT services, including IoT data sharing, data offloading and caching, attack detection, localization, mobile crowdsensing  ...  Federated Learning (FL) has emerged as a distributed collaborative AI approach that can enable many intelligent IoT applications, by allowing for AI training at distributed IoT devices without the need  ...  The work in [205] introduces a software-based deep learning accelerator to support AI/DL training on mobile hardware.  ... 
arXiv:2104.07914v1 fatcat:b5wsrfcbynel7jqdxpfw4ftwh4
« Previous Showing results 1 — 15 out of 1,963 results